Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 7-GEMMASCOPE-RES-16K
    6. 2216
    Prev
    Next
    INDEX
    Explanations

    references to bags and their various types or uses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ']],
    -1.11
     onCancelled
    -1.05
     EPIC
    -0.96
    хьтан
    -0.96
    /**
    -0.95
    ]-->
    -0.95
    EPIC
    -0.95
    "]));
    -0.94
     CommonModule
    -0.91
    ')));
    -0.91
    POSITIVE LOGITS
     bag
    2.33
     bags
    2.24
    bag
    2.16
     Bag
    2.07
    Bag
    2.03
    bags
    1.93
     BAG
    1.93
     Bags
    1.84
    BAG
    1.79
    Bags
    1.66
    Activations Density 0.040%

    No Known Activations